Impact of Feature Selection on EEG Based Motor Imagery

被引：5
作者：
Sahu, Mridu [1 ]
Shukla, Sneha [1 ]
机构：
[1] Natl Inst Technol, Dept IT, Raipur, Chhattisgarh, India
来源：
INFORMATION AND COMMUNICATION TECHNOLOGY FOR COMPETITIVE STRATEGIES | 2019年 / 40卷
关键词：
Motor imagery; Electroencephalography; Short time Fourier transform; Wavelet; Feature selection; BRAIN-COMPUTER INTERFACE; TIME FOURIER-TRANSFORM; FEATURE-EXTRACTION; WAVELET TRANSFORM; CHANNEL SELECTION; CLASSIFICATION;
D O I：
10.1007/978-981-13-0586-3_73
中图分类号：
TP301 [理论、方法];
学科分类号：
081202 ;
摘要：
An EEG based motor imagery translates the motor intention of any subject into control signal by classifying EEG data of different imagination tasks such as hand and feet movements. As indicated by study, it is found that there are almost around 1 in 50 individuals living with loss of motion roughly 5.4 million individuals. For this sort of inability, EEG based BCI for motor imagery of right hand and feet movement imagination is acquired and classified. Short time Fourier transform and wavelet features are extracted and classified with and without feature selection. Ranking method is used for feature selection. Both classification outcomes are comparatively analyzed and observed that there is an increment in classification accuracy when features are classified after feature selection.
引用
收藏
页码：749 / 762
页数：14
相关论文
共 21 条
[1]   Comparison of wavelet transform and FFT methods in the analysis of EEG signals [J].
Akin M. .
Journal of Medical Systems, 2002, 26 (3) :241-247
[2]   THE FRACTIONAL FOURIER-TRANSFORM AND TIME-FREQUENCY REPRESENTATIONS [J].
ALMEIDA, LB .
IEEE TRANSACTIONS ON SIGNAL PROCESSING, 1994, 42 (11) :3084-3091
[3]  
Ang KK, 2010, IEEE ENG MED BIO, P5549, DOI 10.1109/IEMBS.2010.5626782
[4]  
[Anonymous], P 6 INT BRAIN COMP I
[5]   Optimizing the Channel Selection and Classification Accuracy in EEG-Based BCI [J].
Arvaneh, Mahnaz ;
Guan, Cuntai ;
Ang, Kai Keng ;
Quek, Chai .
IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING, 2011, 58 (06) :1865-1873
[6]   Automatic feature selection of motor imagery EEG signals using differential evolution and learning automata [J].
Bhattacharyya, Saugat ;
Sengupta, Abhronil ;
Chakraborti, Tathagatha ;
Konar, Amit ;
Tibarewala, D. N. .
MEDICAL & BIOLOGICAL ENGINEERING & COMPUTING, 2014, 52 (02) :131-139
[7]   Spatial filtering and selection of optimized components in four class motor imagery EEG data using independent components analysis [J].
Brunner, Clemens ;
Naeem, Muhammad ;
Leeb, Robert ;
Graimann, Bernhard ;
Pfurtscheller, Gert .
PATTERN RECOGNITION LETTERS, 2007, 28 (08) :957-964
[8]   Comparison of Wavelet and Short Time Fourier Transform Methods in the Analysis of EMG Signals [J].
Canal, Mehmet Rahmi .
JOURNAL OF MEDICAL SYSTEMS, 2010, 34 (01) :91-94
[9]   Wavelet transform feature extraction from human PPG, ECG, and EEG signal responses to ELF PEMF exposures:: A pilot study [J].
Cvetkovic, Dean ;
Ubeyli, Elif Derya ;
Cosic, Irena .
DIGITAL SIGNAL PROCESSING, 2008, 18 (05) :861-874
[10]   Wavelet-based EEG processing for computer-aided seizure detection and epilepsy diagnosis [J].
Faust, Oliver ;
Acharya, U. Rajendra ;
Adeli, Hojjat ;
Adeli, Amir .
SEIZURE-EUROPEAN JOURNAL OF EPILEPSY, 2015, 26 :56-64
123